Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Quant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ILLE
    -0.07
    ibir
    -0.07
    odel
    -0.07
     Hob
    -0.07
    bows
    -0.07
    ervoir
    -0.07
     Triple
    -0.07
    ीब
    -0.06
    節
    -0.06
     Derby
    -0.06
    POSITIVE LOGITS
     quant
    0.13
     Quant
    0.09
    quant
    0.09
     свет
    0.08
    ]:↵↵
    0.08
    :(
    0.08
     [])↵↵
    0.07
    Quant
    0.07
    uant
    0.07
    ):
↵
↵
    0.07
    Act Density 0.008%

    No Known Activations